TEST #3137 RESULTS
03/20/2026 - 6:57 PM
ACCELERATOR
MODEL
73.9
tokens/s
generation
739
ms
time to first token
1812
tokens/s
prompt
566
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Phenom(tm) 9550 Quad-Core Processor (amdfam10)
RAM
3.6GB
OS
Linux
Kernel Release
6.8.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #101-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 9 10:15:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2136
tokens/s
80.7
tokens/s
492
ms
pp4096+tg256
1606
tokens/s
50.4
tokens/s
2.57
sec
pp2048+tg256
1911
tokens/s
67.5
tokens/s
1.09
sec
pp2048+tg768
1907
tokens/s
64.7
tokens/s
1.09
sec
pp1024+tg1024
2089
tokens/s
75.6
tokens/s
502
ms
pp1280+tg3072
2014
tokens/s
61.0
tokens/s
648
ms
pp384+tg1152
2205
tokens/s
84.8
tokens/s
185
ms
pp64+tg1024
1727
tokens/s
92.5
tokens/s
47
ms
pp16+tg1536
712
tokens/s
88.1
tokens/s
32
ms